{"total":720,"rows":[{"id":"2203.16527","title":"Exploring Plain Vision Transformer Backbones for Object Detection","created":"2022-03-30","cited_by_count":724,"area":null},{"id":"2111.07624","title":"Attention Mechanisms in Computer Vision: A Survey","created":"2021-11-15","cited_by_count":232,"area":null},{"id":"2106.03348","title":"ViTAE: Vision Transformer Advanced by Exploring Intrinsic Inductive Bias","created":"2021-06-07","cited_by_count":216,"area":null},{"id":"2106.00666","title":"You Only Look at One Sequence: Rethinking Transformer in Vision through Object Detection","created":"2021-06-01","cited_by_count":170,"area":null},{"id":"2307.01426","title":"DeepfakeBench: A Comprehensive Benchmark of Deepfake Detection","created":"2023-07-04","cited_by_count":166,"area":null},{"id":"2202.05924","title":"Compute Trends Across Three Eras of Machine Learning","created":"2022-02-11","cited_by_count":163,"area":null},{"id":"2105.01928","title":"Instances as Queries","created":"2021-05-05","cited_by_count":158,"area":null},{"id":"2304.00501","title":"A Comprehensive Review of YOLO Architectures in Computer Vision: From YOLOv1 to YOLOv8 and YOLO-NAS","created":"2023-04-02","cited_by_count":151,"area":null},{"id":"2203.02688","title":"Zoom In and Out: A Mixed-scale Triplet Network for Camouflaged Object Detection","created":"2022-03-05","cited_by_count":145,"area":null},{"id":"2301.08727","title":"Neural Architecture Search: Insights from 1000 Papers","created":"2023-01-20","cited_by_count":139,"area":null},{"id":"2207.14096","title":"Towards Large-Scale Small Object Detection: Survey and Benchmarks","created":"2022-07-28","cited_by_count":122,"area":null},{"id":"2202.10108","title":"ViTAEv2: Vision Transformer Advanced by Exploring Inductive Bias for Image Recognition and Beyond","created":"2022-02-21","cited_by_count":117,"area":null},{"id":"2106.10823","title":"3D Object Detection for Autonomous Driving: A Survey","created":"2021-06-21","cited_by_count":106,"area":null},{"id":"2101.10955","title":"RAPIQUE: Rapid and Accurate Video Quality Prediction of User Generated Content","created":"2021-01-26","cited_by_count":100,"area":null},{"id":"2104.11892","title":"A Survey of Modern Deep Learning based Object Detection Models","created":"2021-04-24","cited_by_count":98,"area":null},{"id":"2301.03580","title":"Designing BERT for Convolutional Networks: Sparse and Hierarchical Masked Modeling","created":"2023-01-09","cited_by_count":94,"area":null},{"id":"2305.09972","title":"Real-Time Flying Object Detection with YOLOv8","created":"2023-05-17","cited_by_count":94,"area":null},{"id":"2210.09071","title":"Attention Attention Everywhere: Monocular Depth Prediction with Skip Attention","created":"2022-10-17","cited_by_count":93,"area":null},{"id":"2106.12011","title":"P2T: Pyramid Pooling Transformer for Scene Understanding","created":"2021-06-22","cited_by_count":84,"area":null},{"id":"2104.05970","title":"Crossover Learning for Fast Online Video Instance Segmentation","created":"2021-04-13","cited_by_count":83,"area":null},{"id":"2108.11539","title":"TPH-YOLOv5: Improved YOLOv5 Based on Transformer Prediction Head for Object Detection on Drone-captured Scenarios","created":"2021-08-26","cited_by_count":83,"area":null},{"id":"2108.11250","title":"YOLOP: You Only Look Once for Panoptic Driving Perception","created":"2021-08-25","cited_by_count":82,"area":"wm"},{"id":"2108.03151","title":"Full-Duplex Strategy for Video Object Segmentation","created":"2021-08-06","cited_by_count":78,"area":null},{"id":"2101.07172","title":"HarDNet-MSEG: A Simple Encoder-Decoder Polyp Segmentation Neural Network that Achieves over 0.9 Mean Dice and 86 FPS","created":"2021-01-18","cited_by_count":71,"area":null},{"id":"2101.11796","title":"DOC2PPT: Automatic Presentation Slides Generation from Scientific Documents","created":"2021-01-28","cited_by_count":70,"area":null},{"id":"2108.08258","title":"LIGA-Stereo: Learning LiDAR Geometry Aware Representations for Stereo-based 3D Detector","created":"2021-08-18","cited_by_count":70,"area":null},{"id":"2301.03505","title":"Advances in Medical Image Analysis with Vision Transformers: A Comprehensive Review","created":"2023-01-09","cited_by_count":62,"area":null},{"id":"2108.10531","title":"Unsupervised Depth Completion with Calibrated Backprojection Layers","created":"2021-08-24","cited_by_count":61,"area":null},{"id":"2106.07873","title":"Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Images","created":"2021-06-15","cited_by_count":58,"area":null},{"id":"2304.10410","title":"Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Review","created":"2023-04-20","cited_by_count":58,"area":null},{"id":"2101.08158","title":"Focal and Efficient IOU Loss for Accurate Bounding Box Regression","created":"2021-01-20","cited_by_count":57,"area":null},{"id":"2410.06245","title":"HiSplat: Hierarchical 3D Gaussian Splatting for Generalizable Sparse-View Reconstruction","created":"2024-10-08","cited_by_count":57,"area":null},{"id":"2101.00443","title":"Semantics for Robotic Mapping, Perception and Interaction: A Survey","created":"2021-01-02","cited_by_count":56,"area":null},{"id":"2103.04260","title":"ARVo: Learning All-Range Volumetric Correspondence for Video Deblurring","created":"2021-03-07","cited_by_count":54,"area":null},{"id":"2103.17115","title":"Dense Relation Distillation with Context-aware Aggregation for Few-Shot Object Detection","created":"2021-03-30","cited_by_count":53,"area":null},{"id":"2105.01294","title":"Hallucination Improves Few-Shot Object Detection","created":"2021-05-04","cited_by_count":50,"area":null},{"id":"2211.10881","title":"Deepfake Detection: A Comprehensive Survey from the Reliability Perspective","created":"2022-11-20","cited_by_count":50,"area":null},{"id":"2310.20208","title":"ZoomNeXt: A Unified Collaborative Pyramid Network for Camouflaged Object Detection","created":"2023-10-31","cited_by_count":48,"area":null},{"id":"2209.13351","title":"SuperYOLO: Super Resolution Assisted Object Detection in Multimodal Remote Sensing Imagery","created":"2022-09-27","cited_by_count":47,"area":null},{"id":"2205.01291","title":"Cross Domain Object Detection by Target-Perceived Dual Branch Distillation","created":"2022-05-03","cited_by_count":46,"area":"distill"},{"id":"2207.01223","title":"A Survey on Label-efficient Deep Image Segmentation: Bridging the Gap between Weak Supervision and Dense Prediction","created":"2022-07-04","cited_by_count":46,"area":null},{"id":"2211.11646","title":"NeRF-RPN: A general framework for object detection in NeRFs","created":"2022-11-21","cited_by_count":46,"area":null},{"id":"2502.17437","title":"Fractal Generative Models","created":"2025-02-24","cited_by_count":46,"area":null},{"id":"2110.01428","title":"Seeking Similarities over Differences: Similarity-based Domain Alignment for Adaptive Object Detection","created":"2021-10-04","cited_by_count":45,"area":null},{"id":"2205.14497","title":"BadDet: Backdoor Attacks on Object Detection","created":"2022-05-28","cited_by_count":45,"area":null},{"id":"2212.03862","title":"Teaching Matters: Investigating the Role of Supervision in Vision Transformers","created":"2022-12-07","cited_by_count":45,"area":null},{"id":"2106.11118","title":"SODA10M: A Large-Scale 2D Self/Semi-Supervised Object Detection Dataset for Autonomous Driving","created":"2021-06-21","cited_by_count":43,"area":null},{"id":"2101.04704","title":"Boundary-Aware Segmentation Network for Mobile and Web Applications","created":"2021-01-12","cited_by_count":42,"area":null},{"id":"2304.04395","title":"Instance Neural Radiance Field","created":"2023-04-10","cited_by_count":40,"area":null},{"id":"2104.10824","title":"Colonoscopy Polyp Detection and Classification: Dataset Creation and Comparative Evaluations","created":"2021-04-22","cited_by_count":38,"area":null},{"id":"2106.02994","title":"Learning Topology from Synthetic Data for Unsupervised Depth Completion","created":"2021-06-06","cited_by_count":38,"area":null},{"id":"2207.12988","title":"Monocular 3D Object Detection with Depth from Motion","created":"2022-07-26","cited_by_count":38,"area":null},{"id":"2211.15444","title":"DAMO-YOLO : A Report on Real-Time Object Detection Design","created":"2022-11-23","cited_by_count":38,"area":null},{"id":"2308.14221","title":"High-Resolution Document Shadow Removal via A Large-Scale Real-World Dataset and A Frequency-Aware Shadow Erasing Net","created":"2023-08-27","cited_by_count":36,"area":null},{"id":"2101.06175","title":"PaddleSeg: A High-Efficient Development Toolkit for Image Segmentation","created":"2021-01-15","cited_by_count":35,"area":null},{"id":"2104.14235","title":"Inspect, Understand, Overcome: A Survey of Practical Methods for AI Safety","created":"2021-04-29","cited_by_count":35,"area":null},{"id":"2212.00776","title":"ResFormer: Scaling ViTs with Multi-Resolution Training","created":"2022-12-01","cited_by_count":34,"area":null},{"id":"2101.09991","title":"UniToPatho, a labeled histopathological dataset for colorectal polyps classification and adenoma dysplasia grading","created":"2021-01-25","cited_by_count":33,"area":null},{"id":"2203.13249","title":"BigDetection: A Large-scale Benchmark for Improved Object Detector Pre-training","created":"2022-03-24","cited_by_count":33,"area":null},{"id":"2301.12276","title":"ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts","created":"2023-01-28","cited_by_count":33,"area":null},{"id":"2308.05480","title":"YOLO-MS: Rethinking Multi-Scale Representation Learning for Real-time Object Detection","created":"2023-08-10","cited_by_count":33,"area":null},{"id":"2101.12463","title":"Robust Representation Learning with Feedback for Single Image Deraining","created":"2021-01-29","cited_by_count":32,"area":null},{"id":"2105.04328","title":"An Autonomous Drone for Search and Rescue in Forests using Airborne Optical Sectioning","created":"2021-05-10","cited_by_count":32,"area":null},{"id":"2108.12102","title":"FOVEA: Foveated Image Magnification for Autonomous Navigation","created":"2021-08-27","cited_by_count":32,"area":null},{"id":"2112.01011","title":"Local Similarity Pattern and Cost Self-Reassembling for Deep Stereo Matching Networks","created":"2021-12-02","cited_by_count":32,"area":null},{"id":"2211.04800","title":"Designing Network Design Strategies Through Gradient Path Analysis","created":"2022-11-09","cited_by_count":32,"area":null},{"id":"2111.14562","title":"Instance-wise Occlusion and Depth Orders in Natural Scenes","created":"2021-11-29","cited_by_count":31,"area":null},{"id":"2203.14898","title":"Learning Where to Learn in Cross-View Self-Supervised Learning","created":"2022-03-28","cited_by_count":31,"area":null},{"id":"2104.10419","title":"PP-YOLOv2: A Practical Object Detector","created":"2021-04-21","cited_by_count":30,"area":null},{"id":"2210.00933","title":"Perceptual Attacks of No-Reference Image Quality Models with Human-in-the-Loop","created":"2022-10-03","cited_by_count":30,"area":null},{"id":"2309.00121","title":"Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation","created":"2023-08-31","cited_by_count":30,"area":null},{"id":"2105.10859","title":"Coarse to Fine Multi-Resolution Temporal Convolutional Network","created":"2021-05-23","cited_by_count":28,"area":null},{"id":"2105.02184","title":"PolarMask++: Enhanced Polar Representation for Single-Shot Instance Segmentation and Beyond","created":"2021-05-05","cited_by_count":27,"area":null},{"id":"2106.15754","title":"Looking Outside the Window: Wide-Context Transformer for the Semantic Segmentation of High-Resolution Remote Sensing Images","created":"2021-06-29","cited_by_count":27,"area":null},{"id":"2201.06192","title":"Fooling the Eyes of Autonomous Vehicles: Robust Physical Adversarial Examples Against Traffic Sign Recognition Systems","created":"2022-01-17","cited_by_count":27,"area":null},{"id":"2208.03641","title":"No More Strided Convolutions or Pooling: A New CNN Building Block for Low-Resolution Images and Small Objects","created":"2022-08-07","cited_by_count":27,"area":null},{"id":"2302.06378","title":"Semantic Image Segmentation: Two Decades of Research","created":"2023-02-13","cited_by_count":27,"area":null},{"id":"2101.00440","title":"Refining activation downsampling with SoftPool","created":"2021-01-02","cited_by_count":26,"area":null},{"id":"2106.03412","title":"Resolution learning in deep convolutional networks using scale-space theory","created":"2021-06-07","cited_by_count":26,"area":null},{"id":"2109.06062","title":"Semantics-Guided Contrastive Network for Zero-Shot Object detection","created":"2021-09-04","cited_by_count":26,"area":null},{"id":"2111.05297","title":"Sliced Recursive Transformer","created":"2021-11-09","cited_by_count":26,"area":null},{"id":"2208.11434","title":"YOLOPv2: Better, Faster, Stronger for Panoptic Driving Perception","created":"2022-08-24","cited_by_count":26,"area":null},{"id":"2310.18954","title":"Mask Propagation for Efficient Video Semantic Segmentation","created":"2023-10-29","cited_by_count":26,"area":null},{"id":"2111.00902","title":"PP-PicoDet: A Better Real-Time Object Detector on Mobile Devices","created":"2021-11-01","cited_by_count":25,"area":null},{"id":"2208.04171","title":"Object Detection Using Sim2Real Domain Randomization for Robotic Applications","created":"2022-08-08","cited_by_count":25,"area":null},{"id":"2212.06969","title":"EgoLoc: Revisiting 3D Object Localization from Egocentric Videos with Visual Queries","created":"2022-12-14","cited_by_count":25,"area":null},{"id":"2305.17473","title":"A Comprehensive Overview and Comparative Analysis on Deep Learning Models: CNN, RNN, LSTM, GRU","created":"2023-05-27","cited_by_count":25,"area":null},{"id":"2309.01439","title":"Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN","created":"2023-09-04","cited_by_count":25,"area":null},{"id":"2401.02456","title":"A comprehensive survey of research towards AI-enabled unmanned aerial systems in pre-, active-, and post-wildfire management","created":"2024-01-04","cited_by_count":25,"area":null},{"id":"2109.06875","title":"Multi-Scale Aligned Distillation for Low-Resolution Detection","created":"2021-09-14","cited_by_count":24,"area":"distill"},{"id":"2204.12037","title":"Causal Reasoning Meets Visual Representation Learning: A Prospective Study","created":"2022-04-26","cited_by_count":24,"area":"lr"},{"id":"2211.10528","title":"Where is my Wallet? Modeling Object Proposal Sets for Egocentric Visual Query Localization","created":"2022-11-18","cited_by_count":24,"area":null},{"id":"2307.14336","title":"MAMo: Leveraging Memory and Attention for Monocular Video Depth Estimation","created":"2023-07-26","cited_by_count":24,"area":null},{"id":"2102.09133","title":"Densely Nested Top-Down Flows for Salient Object Detection","created":"2021-02-18","cited_by_count":23,"area":null},{"id":"2104.05367","title":"Visiting the Invisible: Layer-by-Layer Completed Scene Decomposition","created":"2021-04-12","cited_by_count":23,"area":null},{"id":"2108.03004","title":"MmWave Radar and Vision Fusion for Object Detection in Autonomous Driving: A Review","created":"2021-08-06","cited_by_count":23,"area":null},{"id":"2108.04009","title":"Transductive Few-Shot Classification on the Oblique Manifold","created":"2021-08-09","cited_by_count":23,"area":null},{"id":"2212.11078","title":"C2F-TCN: A Framework for Semi and Fully Supervised Temporal Action Segmentation","created":"2022-12-20","cited_by_count":23,"area":null},{"id":"2102.02531","title":"ABCNet: Attentive Bilateral Contextual Network for Efficient Semantic Segmentation of Fine-Resolution Remote Sensing Images","created":"2021-02-04","cited_by_count":22,"area":null},{"id":"2103.11436","title":"Responsible AI: Gender bias assessment in emotion recognition","created":"2021-03-21","cited_by_count":22,"area":null}],"next_cursor":"100"}